From c961ea41ef58b14e671ccb8bfdb71445c84083b2 Mon Sep 17 00:00:00 2001
From: Fabien Benetou <fabien@benetou.fr>
Date: Sun, 17 Jul 2011 23:24:36 +0200
Subject: [PATCH] non tested but re-organizing from previously working version

---
 shell_scripts/logs_own_vocabulary | 14 ++++++++++++++
 shell_scripts/most_used_commands  | 12 ++++++++----
 2 files changed, 22 insertions(+), 4 deletions(-)
 create mode 100755 shell_scripts/logs_own_vocabulary

diff --git a/shell_scripts/logs_own_vocabulary b/shell_scripts/logs_own_vocabulary
new file mode 100755
index 0000000..260efa0
--- /dev/null
+++ b/shell_scripts/logs_own_vocabulary
@@ -0,0 +1,14 @@
+#! /usr/bin/env bash
+
+# see http://fabien.benetou.fr/innovativ.it/www/HistoricalArchives/Seedea/Oimp/Ubiquitousvocabulary
+
+LOGS=web/thelab/stigmergylive/logs/ChannelLogger/freenode/#*/*
+
+cat $LOGS | grep "<Utopiah" | sed -e "s/[^a-zA-Z]/ /g" | sed -e "s/ /\n/g" | sed -e "s/^.\{1,3\}$//" |sort | uniq
+
+# cleaning by removing low frequency words
+# ... | sed -e "s/[^a-zA-Z]/ /g" | sed -e "s/ /\n/g" | sed -e "s/^.\{1,3\}$//" |sort | uniq -c | grep -v " 1" | grep -v " 2" | grep -v " 3" | wc -l
+
+# 10 most commonly used words
+# ... | sed -e "s/[^a-zA-Z]/ /g" | sed -e "s/ /\n/g" | sed -e "s/^.\{1,3\}$//" |sort | uniq -c | sort -n | tail -15
+
diff --git a/shell_scripts/most_used_commands b/shell_scripts/most_used_commands
index 1a63cde..b26b873 100755
--- a/shell_scripts/most_used_commands
+++ b/shell_scripts/most_used_commands
@@ -1,6 +1,14 @@
 #! /usr/bin/env bash
 AVOID="con\|utopiah@benetou.fr"
 
+# TODO
+#	consider similar usage for more than bash
+#		find ~ -name "*history*"
+#		~/.vimperator/info/default/history-command (specific JSON format)
+#		~/.newsbeuter/history.cmdline
+#		code repository per programming language (PHP, Processing, JavaScript, ... and bash too!)
+#			thought about this earlier to compare with the "signature" vocabulary of expert, notes unfound	
+
 echo consider also http://fabien.benetou.fr/Tools/ and to do exercises
 # warning, do not miss the environment e.g. http://mywiki.wooledge.org/BashGuide/
 
@@ -8,7 +16,3 @@ cat ~/.bash_history | sed "s/ /\n/g" | grep "^[[:alpha:]]" | sort | uniq -c | gr
 # simpler version for just the first word, which is bad for commands like sort which never appear first
 #cat ~/.bash_history | sed "s/ .*//" | sort  | uniq -c | sort -n | tail
 
-# consider similar usage for more than bash
-# find ~ -name "*history*"
-# ~/.vimperator/info/default/history-command (specific JSON format)
-# ~/.newsbeuter/history.cmdline